AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆312Nov 1, 2024Updated last year
Alternatives and similar repositories for AlignProp
Users that are interested in AlignProp are comparing it to the libraries listed below
Sorting:
- DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support☆746Mar 22, 2024Updated last year
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆554Jul 5, 2023Updated 2 years ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆666Nov 10, 2025Updated 3 months ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆647May 24, 2024Updated last year
- ☆580Dec 21, 2024Updated last year
- [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation☆1,641Oct 29, 2025Updated 4 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆242Apr 6, 2024Updated last year
- [ICLR 2024 Spotlight] Official implementation of ScaleCrafter for higher-resolution visual generation at inference time.☆510Mar 7, 2024Updated last year
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆309Mar 12, 2025Updated 11 months ago
- The official repository of paper "ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection" (N…☆50Oct 23, 2023Updated 2 years ago
- [NeurIPS 2024] 💫CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching☆168Nov 18, 2024Updated last year
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆164Sep 15, 2025Updated 5 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]☆178Dec 2, 2025Updated 3 months ago
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆265Apr 7, 2025Updated 10 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆294Jul 14, 2023Updated 2 years ago
- [ICLR 2024] Code for FreeNoise based on VideoCrafter☆427Aug 25, 2025Updated 6 months ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆298Aug 29, 2025Updated 6 months ago
- CLIP+MLP Aesthetic Score Predictor☆1,261Jul 1, 2024Updated last year
- ☆73Jan 27, 2025Updated last year
- PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis☆3,281Oct 31, 2024Updated last year
- Diffusion Reinforcement Learning Library☆194Feb 13, 2024Updated 2 years ago
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,936Aug 15, 2024Updated last year
- Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning☆316Jul 11, 2024Updated last year
- Official Pytorch Implementation of DenseDiffusion (ICCV 2023)☆501Nov 14, 2023Updated 2 years ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆82Jun 11, 2024Updated last year
- SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all…☆30Jul 18, 2024Updated last year
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆534Sep 8, 2025Updated 5 months ago
- [ICLR 2024] Github Repo for "HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion"☆498Oct 14, 2023Updated 2 years ago
- FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)☆1,895Dec 24, 2024Updated last year
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆86Jul 16, 2024Updated last year
- [ICCV 2023] Consistent Image Synthesis and Editing☆840Aug 19, 2024Updated last year
- Concept Sliders for Precise Control of Diffusion Models☆1,131Jun 20, 2025Updated 8 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆153Jun 25, 2024Updated last year
- ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation (ICCV 2023, Oral)☆543Jan 8, 2024Updated 2 years ago
- Consistency Distilled Diff VAE☆2,209Nov 7, 2023Updated 2 years ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆40May 9, 2024Updated last year
- InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)☆1,386Jun 7, 2024Updated last year
- ICLR 2024 (Spotlight)☆785Mar 2, 2024Updated 2 years ago
- LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation☆134Oct 25, 2023Updated 2 years ago